Rechercher des ressources

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Even though annotations already declare readOnlyHint and idempotentHint, the description adds substantial behavioral context: server-side filtering, paginated list, sort semantics, AND/OR logic for tools, and the need to consult the dictionary for IDs. It also clarifies that geolocation requires geoDistance and that keywordsType changes the keyword search scope, making behavior more transparent than annotations alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every section serves a purpose: overview, bulleted use cases, sorting, and result handling. It is well-structured with bold labels and examples, making dense information scannable. No fluff or redundant restatement of schema content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 34 optional parameters, the description covers major usage patterns, combinations, and caveats (e.g., dictionary IDs, format requirements, pagination). It points to related tools for detail and relies on the output schema for return structure, which is appropriate. The guidance is sufficient for an agent to select and call this tool effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although the schema has 100% parameter description coverage, the description greatly enhances semantic understanding with concrete examples and cross-parameter relationships (e.g., perimeterDynamic values, tools #AND# syntax, languages 'langueId|niveauId', coordinates+geoDistance). It explains how to get dictionary IDs and which endpoints provide them, adding meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Recherche des ressources (collaborateurs internes) dans BoondManager avec filtres serveur' – a specific verb and resource, clarifying that it searches internal resources only. This distinguishes it from sibling tools like boond_candidates_search and boond_resources_get, and the title 'Rechercher des ressources' is enriched with scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit use cases with concrete parameter combinations (e.g., perimeterDynamic for own data/team/agencies, perimeterManagers for a person's team, period for availability). It ends with 'Utiliser boond_resources_get ou les outils d'onglets pour le détail', directly naming alternatives for further detail, and references boond_application_current_user for obtaining one's own ID.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.